[upstream-sync] README.md from ARUNAGIRINATHAN-K/awesome-ai-agents-2026@7abefb40 [catalogue]

Reviewed-on: #14

upstream/ARUNAGIRINATHAN-K-awesome-ai-agents-2026/catalogue/README.md

@@ -2,9 +2,9 @@
 title: "Awesome AI Agents 2026"
 task: ""
 lineage_type: import
-upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/cf7945ae/README.md
-upstream_sha: cf7945ae
-imported_at: 2026-07-02
+upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/7abefb40/README.md
+upstream_sha: 7abefb40
+imported_at: 2026-07-05
 prompt_class: catalogue
 upstream_changes: accepted
 author: upstream
@@ -155,6 +155,7 @@ validated: false
 - [Qdrant](https://github.com/qdrant/qdrant) `🌱` `[Rust]` `[Vector DB]` - High-performance vector similarity search engine with rich payload filtering for agent memory.
 - [RAGFlow](https://github.com/infiniflow/ragflow) `🌱` `[Python]` `[RAG]` - Open-source RAG engine with agent capabilities and deep document understanding for knowledge bases.
 - [SimpleMem](https://github.com/aiming-lab/SimpleMem) `🌱` `[Python]` `[Multimodal]` - Efficient lifelong memory for LLM agents supporting both text and multimodal inputs.
+- [Superdense](https://github.com/Nimrobo/superdense) `🔬` `[TypeScript]` `[Memory]` - Gives coding agents persistent memory of what worked across sessions, tracked against real-world outcomes.
 - [Supermemory](https://github.com/supermemoryai/supermemory) `🌱` `[TypeScript]` `[Vector DB]` - Extremely fast and scalable memory engine and API designed for the AI era.
 - [Vestige](https://github.com/samvallad33/vestige) `🌱` `[Rust]` `[MCP]` - Provides local-first memory for coding agents with FSRS-6 retention, active forgetting, and correction tools.
 - [Weaviate](https://github.com/weaviate/weaviate) `🌱` `[Go]` `[Vector DB]` - Stores and searches vector embeddings with hybrid keyword and semantic retrieval for agent knowledge.
@@ -748,6 +749,7 @@ Tools for running LLMs locally and self-hosting AI agent platforms with full pri
 - [LM Studio](https://lmstudio.ai) `🌱` `[TypeScript]` `[Local]` - Desktop application for running local LLMs with a polished UI across all major platforms.
 - [LocalAI](https://github.com/mudler/LocalAI) `🚀` `[Go]` `[OpenAI]` - Drop-in OpenAI API replacement that runs models locally without requiring a GPU.
 - [Ollama](https://github.com/ollama/ollama) `🚀` `[Go]` `[GitHub]` - Run LLMs locally with a dead-simple CLI interface and 162K+ GitHub stars.
+- [RustFox](https://github.com/chinkan/RustFox) `🔬` `[Rust]` `[MCP]` - Self-hosted Telegram AI assistant written in Rust with sandboxed tool execution, MCP integration, and multi-agent orchestration.
 - [vLLM](https://github.com/vllm-project/vllm) `🚀` `[Python]` `[Local]` - High-throughput LLM serving engine with PagedAttention for production-grade local inference.
 - [Yao Agents](https://github.com/YaoApp/yao) `🌱` `[Go]` `[MCP]` - Local-first AI execution platform with Docker sandbox isolation, BYOK model configuration, MCP support, 5-stage Pipeline, and multi-platform messaging via WeChat, Feishu, DingTalk, Telegram, and Discord.
 
@@ -767,6 +769,7 @@ Frameworks and tools for AI risk management, regulatory compliance, and governan
 
 AI agents specialized in penetration testing, vulnerability discovery, threat detection, and security analysis.
 
+- [Dark-Moon](https://github.com/ASCIT31/Dark-Moon) `🌱` `[Python]` `[MCP]` - Autonomous AI penetration testing platform orchestrating 80+ offensive tools via MCP across web, cloud, Active Directory, Kubernetes, and API targets.
 - [Microsoft Security Copilot](https://www.microsoft.com/en-us/security/business/ai-machine-learning/microsoft-security-copilot) `🚀` `[Cloud]` `[Microsoft]` - Enterprise threat detection and incident response AI integrated across Microsoft security products.
 - [PentestGPT](https://github.com/GreyDGL/PentestGPT) `🌱` `[Python]` `[CLI]` - GPT-powered penetration testing tool with automated reasoning for vulnerability assessment.
 - [YAWNING TITAN](https://github.com/dstl/YAWNING-TITAN) `🌱` `[Python]` `[Graph-Based]` - Graph-based cybersecurity simulation environment for training and testing defensive AI agents.

upstream/VoltAgent-awesome-ai-agent-papers/catalogue/README.md

@@ -2,9 +2,9 @@
 title: "Awesome AI Agent Papers"
 task: ""
 lineage_type: import
-upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/d467d641/README.md
-upstream_sha: d467d641
-imported_at: 2026-06-26
+upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/aa50c0c3/README.md
+upstream_sha: aa50c0c3
+imported_at: 2026-07-03
 prompt_class: catalogue
 upstream_changes: accepted
 author: upstream
@@ -75,6 +75,7 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
 
 | Paper | arXiv ID |
 |---|:---:|
+| **[PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation](https://arxiv.org/pdf/2606.05697)** - A persona-conditioned framework that predicts how a specific user would answer UI/UX evaluation questions and explains why in natural language. Trained via contrastive reflection fine-tuning and reflective prompt evolution, reaching human-level realism and generalizing to unseen questions and personas. | <a href="https://arxiv.org/abs/2606.05697"><img src="https://img.shields.io/badge/arXiv-2606.05697-b31b1b.svg" alt="arXiv" /></a> |
 | **[AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing](https://arxiv.org/pdf/2602.17607)** - A multi-agent pipeline that reads a PDE problem description in plain text and writes, debugs, and validates a classical numerical solver end-to-end. Generates spectral and finite-difference code (no neural networks), scoring ~6 orders of magnitude below FNO and CodePDE baselines. | <a href="https://arxiv.org/abs/2602.17607"><img src="https://img.shields.io/badge/arXiv-2602.17607-b31b1b.svg" alt="arXiv" /></a> |
 | **[Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluation](https://arxiv.org/abs/2604.09549)** - Evaluates recommender systems via agent-RS interactions. | <a href="https://arxiv.org/abs/2604.09549"><img src="https://img.shields.io/badge/arXiv-2602.06039-b31b1b.svg" alt="arXiv" /></a> |
 | **[CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://arxiv.org/pdf/2604.01658)** - Introduces long-running multi-agent systems that self-evolve via shared persistent memory, asynchronous execution, and heartbeat-based interventions; 3–10× higher improvement rates than fixed evolutionary-search baselines on 10 math/algorithmic/systems tasks. | <a href="https://arxiv.org/abs/2604.01658"><img src="https://img.shields.io/badge/arXiv-2604.01658-b31b1b.svg" alt="arXiv" /></a> |
@@ -211,6 +212,7 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
 
 | Paper | arXiv ID |
 |---|:---:|
+| **[PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://arxiv.org/pdf/2606.08878)** - A 110-scenario benchmark testing whether LLMs can compose orchestration prompts that distribute context to sub-agents without information leakage. Across 10 topologies and 27 commercial models, GPT-5.5 leads with 62% pass rate while the average is 14.9%. | <a href="https://arxiv.org/abs/2606.08878"><img src="https://img.shields.io/badge/arXiv-2606.08878-b31b1b.svg" alt="arXiv" /></a> |
 | **[ClawBench: Evaluating Browser Agents on Live Production Websites with Submission-Interception](https://arxiv.org/abs/2604.08523)** - Benchmarks browser agents on 283 everyday tasks (V1 153 + V2 130) across 163 live production sites, with a Chrome-extension plus CDP layer that blocks only the final write request so agents can run end-to-end on real sites without real-world side effects. Two-stage scoring (interception + LLM judge); leaderboard at https://claw-bench.com. | <a href="https://arxiv.org/abs/2604.08523"><img src="https://img.shields.io/badge/arXiv-2604.08523-b31b1b.svg" alt="arXiv" /></a> |
 | **[From Features to Actions: Explainability in Traditional and Agentic AI Systems](https://arxiv.org/pdf/2602.06841v1)** - Compares attribution-based explanations with trace-based diagnostics across static and agentic settings to study how explainability methods translate to multi-step agent trajectories. | <a href="https://arxiv.org/abs/2602.06841v1"><img src="https://img.shields.io/badge/arXiv-2602.06841-b31b1b.svg" alt="arXiv" /></a> |
 | **[Agentic Uncertainty Reveals Agentic Overconfidence](https://arxiv.org/pdf/2602.06948v1)** - Investigates whether agents can accurately predict their own success rates in agentic tasks. | <a href="https://arxiv.org/abs/2602.06948v1"><img src="https://img.shields.io/badge/arXiv-2602.06948-b31b1b.svg" alt="arXiv" /></a> |
@@ -297,12 +299,13 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
 <br>
 
 <details id="agent-tooling">
-<summary><h3 style="display:inline">Agent Tooling (95)</h3></summary>
+<summary><h3 style="display:inline">Agent Tooling (96)</h3></summary>
 
 <br>
 
 | Paper | arXiv ID |
 |---|:---:|
+| **[On Effectiveness and Efficiency of Agentic Tool-calling and RL Training](https://arxiv.org/pdf/2606.00135)** - Find that current agentic tool-calling benchmarks like BFCL are quite brittle: system prompt, multi-turn template or even pure random seeds could have huge influence on the final performance. | <a href="https://arxiv.org/abs/2606.00135"><img src="https://img.shields.io/badge/arXiv-2602.06875-b31b1b.svg" alt="arXiv" /></a> |
 | **[TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging](https://arxiv.org/pdf/2602.06875v1)** - Proposes a multi-agent observe-analyze-repair loop that uses runtime traces to find and fix bugs in LLM-generated code. | <a href="https://arxiv.org/abs/2602.06875v1"><img src="https://img.shields.io/badge/arXiv-2602.06875-b31b1b.svg" alt="arXiv" /></a> |
 | **[Generative Ontology: When Structured Knowledge Learns to Create](https://arxiv.org/pdf/2602.05636v1)** - Explores constraining LLM generation with executable schemas and multi-agent roles to produce structurally valid yet creative outputs. | <a href="https://arxiv.org/abs/2602.05636v1"><img src="https://img.shields.io/badge/arXiv-2602.05636-b31b1b.svg" alt="arXiv" /></a> |
 | **[Structured Context Engineering for File-Native Agentic Systems](https://arxiv.org/pdf/2602.05447v1)** - Tests how context format (YAML, JSON, Markdown) affects agent accuracy across 9,649 experiments in file-native agentic systems. | <a href="https://arxiv.org/abs/2602.05447v1"><img src="https://img.shields.io/badge/arXiv-2602.05447-b31b1b.svg" alt="arXiv" /></a> |